Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4718 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0999. Min Act: -0.0001

Data Index: 242580 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0001

Data Index: 520471 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0975. Min Act: -0.0001

Data Index: 903600 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0991. Min Act: -0.0001

Data Index: 563622 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0958. Min Act: -0.0001

Data Index: 301385 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0950. Min Act: -0.0001

Data Index: 771645 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0938. Min Act: -0.0001

Data Index: 183515 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0942. Min Act: -0.0001

Data Index: 622105 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0941. Min Act: -0.0001

Data Index: 226521 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0945. Min Act: -0.0001

Data Index: 806608 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0898. Min Act: -0.0001

Data Index: 21690 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0874. Min Act: -0.0001

Data Index: 900350 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1083543 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0900. Min Act: -0.0001

Data Index: 384549 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1313080 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1215653 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0877. Min Act: -0.0001

Data Index: 119081 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0879. Min Act: -0.0001

Data Index: 379441 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1147260 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0839. Min Act: -0.0001

Data Index: 675435 (C4 (Web Text))

Max Activating Token Index: 938